{"as_of":"2026-08-08T21:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17050c1d2ff44673914892cdb4a8c405b814e80436429801ffa933019e540f37","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:46:50.822495Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T05:55:56.412874Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.01753","last_updated":"2022-08-02T21:03:48Z","snapshot_observed_at":"2026-08-03T16:31:26.021539Z","submitted_at":"2022-08-02T21:03:48Z","title":"Two-Stream Transformer Architecture for Long Video Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01753","snapshot_observed_at":"2026-08-07T14:46:50.822495Z","title":"Two- stream transformer architecture for long video understand- ing.arXiv preprint arXiv:2208.01753, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03162","last_updated":"2026-07-02T18:35:58Z","snapshot_observed_at":"2026-08-07T14:39:35.718834Z","submitted_at":"2025-05-23T10:41:45Z","title":"FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:50.822495Z"},"links":{"cited_paper":"/paper/2208.01753","citing_paper":"/paper/2506.03162"},"observation_digest":"sha256:d3bdc3573bb751c96d5b90b95de78d457aa33b8340bc47f8ef99d61583907334","observation_id":"96cbeab9-81e8-4370-af05-73014757d86c","resolution":{"observed_at":"2026-08-07T14:46:50.822495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01753","last_updated":"2022-08-02T21:03:48Z","snapshot_observed_at":"2026-08-03T16:31:26.021539Z","submitted_at":"2022-08-02T21:03:48Z","title":"Two-Stream Transformer Architecture for Long Video Understanding","version":1},"cited_work":{"arxiv_id":"2208.01753","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.01753","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"& Gilbert, A","venue":null,"work_id":"6857be4a-d081-4201-8934-c7f3ccd9ce0e","year":2022},"citing_paper":{"arxiv_id":"2604.07578","last_updated":"2026-04-08T20:34:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-08T20:34:47Z","title":"MSGL-Transformer: A Multi-Scale Global-Local Transformer for Rodent Social Behavior Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T17:54:02.755626Z"},"links":{"cited_paper":"/paper/2208.01753","citing_paper":"/paper/2604.07578"},"observation_digest":"sha256:7c7391e533fe439c71e0aed07000a1051a33b2aedfec7be4e274a71a1f0939b5","observation_id":"55d419e5-edc7-4c3a-a0f8-8da73e3f6e93","resolution":{"observed_at":"2026-05-11T05:55:56.421106Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2208.01753/citation-record","integrity":"/paper/2208.01753/integrity","json":"/paper/2208.01753/citation-record.json","paper":"/paper/2208.01753"},"outbound":[],"paper":{"arxiv_id":"2208.01753","last_updated":"2022-08-02T21:03:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T16:31:26.021539Z","submitted_at":"2022-08-02T21:03:48Z","title":"Two-Stream Transformer Architecture for Long Video Understanding"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2208.01753."}